|Publication number||US6138100 A|
|Application number||US 09/059,912|
|Publication date||Oct 24, 2000|
|Filing date||Apr 14, 1998|
|Priority date||Apr 14, 1998|
|Publication number||059912, 09059912, US 6138100 A, US 6138100A, US-A-6138100, US6138100 A, US6138100A|
|Inventors||Dawn L. Dutton, Shrikanth Sambasivan Narayanan, Ilija Zeljkovic|
|Original Assignee||At&T Corp.|
|Export Citation||BiBTeX, EndNote, RefMan|
|Patent Citations (5), Non-Patent Citations (8), Referenced by (112), Classifications (25), Legal Events (6)|
|External Links: USPTO, USPTO Assignment, Espacenet|
The invention relates to voice-activated connection (VAC) systems in general. More particularly, the invention relates to a method and apparatus for constructing an interface for use with a VAC system while minimizing the amount of information required for input by the user.
Recent developments in the fields of speech-recognition, natural language systems and high-speed networking have greatly contributed to the advancement of VAC systems. It is now possible for a person to pick up a telephone handset and initiate a call by uttering simple voice commands such as "call mom" or "call home," rather than using the old-fashioned telephone keypad to dial a telephone number. One such system is described in U.S. Pat. No. 5,719,921. In fact, users with speakerphones no longer need to even use a telephone handset to initiate calls. Specifically, a speakerphone user can simply power on the speakerphone, utter commands in the user's language (e.g., English or Spanish) to request a call connection to another person, and sit back while the call is completed by the system.
The aforementioned functionality provided by VAC systems stems from a combination of several different technologies. Prominent among such technologies are speech-recognition systems and natural language systems, both of which are well-known in the art. A short description of each such technology, however, may prove beneficial to a better understanding of the problems that are solved by the present invention.
Modern speech recognition systems are predicated on the premise that any speech can be broken down into a sequence of sounds selected from a set of approximately forty such sounds called "phonemes". Different sounds, or phonemes, are produced by varying the shape of the vocal tract through muscular control of the speech articulators (e.g., lips, tongue, jaw, etc.). Speech recognition systems basically provide transcription of spoken utterance to a string of phonemes. A stream of a particular sequence of phonemes collectively represents a word or a phrase. In essence, speech recognition systems operate by identifying and analyzing the elemental phonemes contained in a speech signal in order to recognize the word or phrase associated with such phonemes. Hence, for speech recognition systems to be useful, they need to be embodied with the concept of language (e.g., syntax and semantics). The natural language systems provide that capability.
While speech-recognition systems afford VAC systems the ability to recognize certain words and phrases, natural language systems aim at providing rules that constitute words and phrases (language grammar rules) and attaching a meaning to the words and phrases that are recognized (language understanding). Natural language systems operate as a front-end system between a user and the VAC system providing a means for a conversational interface between the user and a machine. In other words, the natural language interface translates the language spoken by the user (e.g., English) into a language that is understandable by the target computer system. The translation function of natural language systems is accomplished through the use of a grammar that characterizes a set of acceptable input strings (or more generally, a statistical language model). This enables the speech recognition system to transcribe a spoken utterance into words and phrases as governed by the given language model. The language understanding component of the natural language system receives the output of the speech recognition system as its input. The language understanding component embodies rules and algorithms constituting a language parser (e.g., heuristics or statistical models) which produce a parse tree for the input string. The parse tree is then translated into an expression (or set of expressions) which assigns to the input string a meaning that is interpretable by the target computer system.
Both speech recognition systems and natural language systems share a common element in that they both perform better with a larger number of reference patterns (e.g., phonological information or speech templates for voice recognition systems, word and phrase patterns for natural language systems). For natural language systems, the larger the vocabulary of the system, the more flexible and user-friendly the system becomes. For example, it is easier for a person to communicate a message to another person with a vocabulary of one thousand words than three hundred words. Similarly, it is easier to communicate with a computer with a larger vocabulary of commonly understood terms. Furthermore, a larger vocabulary is more likely to accommodate the varied speaking styles and idiosyncrasies of different people. This larger vocabulary also helps speech-recognition systems, since a larger vocabulary tends to allow a speaker to construct longer phrases, and the performance of many conventional speech-recognition systems in general tends to improve when multiple words are spoken as compared to short or single words.
Because VAC systems use speech-recognition systems and natural language systems the advantages of a large vocabulary enjoyed by those systems extend to VAC systems as well. Moreover, a large vocabulary provides additional benefits for users of VAC systems. For example, VAC systems enable users to perform a variety of telephony user operations, such as calling, messaging and call forwarding by speaking names from a personally configured list of names or from a generic list provided by a service provider. It is often desirable to enhance the flexibility of the VAC lists by the association of additional attributes to each name in the list, such as a place of work or residence, or the type of service (e.g., cellular or pager). Further, more generally, it is desirable to automatically include other entries (telephone numbers, fax numbers, email address) related to a particular entry (for example, if only the work number of a particular user is originally specified in the user-configured list, automatically retrieve and enter all other available numbers such as pager, cellular, fax, and home and other pertinent information such as email, URL address etc. to the list). The additional attributes and entries to a user's list allow the VAC systems to provide enhanced services and functionality to a user. For example, when a user utters a command, such as "call mom" to a VAC system, a telephone call is automatically initiated and directed to the called party associated with that command. However, the called party may have more than one telephone number. In such a case, it would be desirable for the VAC system to query the user for the type of phone number to be dialed, such as the home number, the office number or the telephone number of the called party's wireless telephone set.
In current VAC systems, however, such additional attributes are required to be explicitly specified by the user, either by voice or text entries. While such an approach has the advantage of allowing the user to have better control over their VAC list, adding such additional attributes becomes tedious and time-consuming for the user. For example, a user would have to--at a minimum--enter a ten digit telephone number and a word or phrase for use as an identification tag for the number, not to mention any additional attributes a user might want to associate with the number (e.g., an address). Combine this with the need to input multiple entries/called parties to the calling list and the burden upon the user becomes even worse. One other problem is to update and keep the information contained these lists current, a task that is tedious to accomplish manually.
In addition to the above disadvantages, the user may not have ready access to additional attributes for the called party. This means the user must first find the information through another source prior to entry. In some instances, the user may not have access to the resources providing such information, such as those stored on a private network or even public networks such as the Internet or World Wide Web (WWW).
In view of the foregoing, it can be appreciated that a substantial need exists for an interface for a VAC system which solves the above-discussed problems.
The present disclosure is directed to a method and apparatus for automatically retrieving from pre-defined databases information to be added to bank of data for a VAC system. In an embodiment of the principles disclosed herein, a user who wishes to create a new entry provides certain information to a VAC system. The VAC system uses the user-provided information, or a portion thereof, as a search key to query pre-defined databases. To illustrate the principles of the present disclosure, let us consider the case of a first person who desires to add a second person to a calling list for use with a VAC system. The first person sends a request to the VAC system to add the second person to a calling list. The request may include, for example, a first information item that uniquely identifies the second person, e.g., a telephone number. The VAC system then launches a query to at least one pre-defined database for additional information items indexed by the first information item. The additional information items may be used as search keys to retrieve from other pre-defined databases supplementary information items. This process continues until the VAC system has gathered sufficient information items related to the second person to construct a natural language grammar for use with the VAC system. Examples of additional information items include the second person's office telephone number, pager number, the telephone number of the second person wireless telephone set, the second person's home address, work address, e-mail address, home page URL, neighbor's address and, employer information, to name a few. Once all the appropriate information items have been gathered by the VAC system, then the VAC system uses the natural language grammar to parse commands given by the first person to request future communications connections (e.g., voice connections) with the second person.
With these and other advantages and features of the invention that will become hereinafter apparent, the nature of the invention may be more clearly understood by reference to the following detailed description of the invention, the appended claims and to the several drawings herein.
FIG. 1 is a block diagram of a telecommunications system which is suitable to practice one embodiment of the present invention.
FIG. 2 is a block diagram of a VAC adjunct in accordance with one embodiment of the present invention.
FIG. 3 is a block flow diagram of the steps performed by a VAC adjunct in accordance with one embodiment of the invention.
Referring now in detail to the drawings wherein like parts are designated by like reference numerals throughout, there is illustrated in FIG. 1 a diagram of a telecommunications system 122 which is suitable to practice one embodiment of the present invention. Audio interface devices, such as telephones 100 and 112, are connected to local exchange carriers (LEC) 102 and 110, respectively. Audio interface devices other than a telephone may also be used. For example, the audio interface device could be a multimedia computer having telephony capabilities. LECs 102 and 110 are connected to switches 104 and 108, respectively, which are both connected to a communication network 106 such as the public switched telephone network (PSTN). In this embodiment of the invention, communication network 106 is a long distance telephone network, and switches 104 and 108 can be nodes in communication network 106 or in LECs 102 and 110. Communication network 106 would generally have other switches similar to switches 104 and 108 for routing calls. However, only two switches are shown in FIG. 1 for clarity. Upon receipt of the call at switch 104 or 108, the call is then routed to a VAC adjunct 114 via communication network 106 and link 124. Thus, there is established an audio channel between telephone 100 or 112 and VAC adjunct 114. The routing of calls through a telecommunications network is well known in the art and will not be described further herein. VAC adjunct 114 is connected to Internet 116 via link 126. VAC adjunct 114 can access a database 118 and web server 120 via Internet 116.
FIG. 2 is a block diagram of a VAC adjunct in accordance with one embodiment of the present invention. VAC adjunct 114 comprises a telephone network interface module 210, a dual-tone multiple frequency (DTMF) decoder/generator 212, a speech recognition module 214, a natural language interface module 216 and a VAC control module 218, each of which is connected to an audio bus 220 and a control/data bus 222. Further, VAC adjunct 114 contains a central processing unit (CPU) 224, memory unit 226, a database 234 and a network interface 232, each of which is connected to control/data bus 222.
The overall functioning of VAC adjunct 114 is controlled by CPU 224. CPU 224 operates under control of executed computer program instructions 228 and data 230 which are stored in memory unit 226. The control of an apparatus, such as VAC adjunct 114, using a central processing unit executing software instructions is well known in the art and will not be described in further detail herein.
Memory unit 226 may be any machine readable storage device, such as random access memory (RAM), a read only memory (ROM), a programmable read only memory (PROM), an erasable programmable read only memory (EPROM), an electronically erasable programmable read only memory (EEPROM), a magnetic storage media (i.e., a magnetic disk), or an optical storage media (i.e., a CD-ROM). Further, VAC adjunct 114 may contain various combinations of machine readable storage devices, which are accessible by CPU 224, and which are capable of storing a combination of computer program instructions 228 and data 230.
Network interface 232 is used for communications between VAC adjunct 114 and web server 120 or database 118. Upon receipt of a call from telephone 100 or 112, VAC adjunct 114 establishes a communication channel with web server 120 or database 118 via network interface 232. In a WWW embodiment, a transmission control protocol/internet protocol (TCP/IP) socket connection is established according to principles well known in the art. For additional information on TCP/IP, see Comer, Douglas, Internetworking with TCP/IP: Principles, Protocols, and Architecture, Englewood Cliffs, N.J., Prentice Hall, 1988, which is incorporated by reference herein. VAC adjunct 114 communicates with web server 120 or database 118 using a document serving protocol. As used herein, a document serving protocol is a communication protocol for the transfer of information between a client and a server. In accordance with such a protocol, a client requests information from a server by sending a request to the server and the server responds to the request by sending a document containing the requested information to the server. Thus, a document serving protocol channel is established between VAC adjunct 114 and web server 120 or database 118. In an advantageous WWW embodiment, the document serving protocol is the Hypertext Transfer Protocol (HTTP). This protocol is well known in the art of WWW communication and is described in detail in Berners-Lee, T. and Connolly, D., Hypertext Transfer Protocol (HTTP) Working Draft of the Internet Engineering Task Force, 1993 which is incorporated herein by reference.
Thus, VAC adjunct 114 communicates with web server 120 or database 118 using the HTTP protocol. As far as web server 120 or database 118 is concerned, it behaves as if were communicating with any conventional WWW client executing a conventional graphical browser. Thus, web server 120 or database 118 serves documents to VAC adjunct 114 in response to requests it receives over link 126. A document, as used herein, is a collection of information. The document may be a static document in that the document is pre-defined at web server 120 or database 118 and all requests for that document result in the same information being served. Alternatively, the document could be a dynamic document, whereby the information which is served in response to a request is dynamically generated at the time the request is made. Typically, dynamic documents are generated by scripts, which are programs executed by web server 120 or database 118 in response to a request for information. For example, a Uniform Resource Locator (URL) may be associated with a script. When web server 120 or database 118 receives a request including that URL, it will execute the script to generate a dynamic document, and will serve the dynamically generated document to the client which requested the information. The use of scripts to dynamically generate documents is well known in the art.
The telephone network interface module 210 handles the low level interaction between VAC adjunct 114 and communication network 106 in general, and switches 104 and 108 in particular. In one embodiment, module 210 consists of one or more analog tip/ring loop start telephone line terminations. Through module 210, CPU 224 is able to control link 124 via control data bus 222. Control functions include on-hook/off-hook, ring detection, and far-end on-hook detection. In an alternate embodiment, module 210 includes one or more channelized digital interfaces, such as T1/DS1, E1, or PR1. Signaling can be in-band or out-of-band.
DTMF decoder/generator 212 handles the conversion of DTMF tones from telephone 100 or 112 into digital data. DTMF decoder/generator 212 also handles the generation of DTMF tones from digital data. DTMF tones are another means by which a user can input information items such as names, addresses, telephone numbers and user options for VAC adjunct 114, in addition to that provided by speech recognition module 214.
Speech recognition module 214 performs speech recognition of speech signals originating at user telephone 100 or 112 and received over audio bus 220. Such speech signals are processed and converted into digital data by speech recognition module 214. Module 214 receives an audio signal over audio bus 220. The audio signal is converted to a corresponding electrical format, and then is electrically conditioned into a form suitable for digital sampling. Once the audio speech signal has been converted to a representative electrical signal, it is received by an analog-to-digital (A/D) converter. The A/D converter samples the representative electrical signal at a suitable sampling rate, and outputs a digitized audio signal. The digitized audio signal is then processed to extract various time-domain and frequency-domain sound characteristics, that are used as a basis for identifying a particular phoneme sound type that is contained within the audio speech signal. It is worthy to note that the functions of module 214 may be implemented in other parts of telecommunication system 122. For example, A/D and D/A conversion could be implemented in switch 104 or 108 and still fall within the scope of the invention.
Natural language module 216 builds a grammar for VAC adjunct 114, and translates natural language statements into instructions for CPU 224. Natural language module 216 employs a grammar which characterizes a set of acceptable input strings (or a statistical language model such as a bigram model). This language model is employed by the speech recognition module 214 to produce an output string that is comprised of a word or phrase sequence as governed by the language (syntax) model. The output string of the speech recognition module serves as input to the language understanding component of the Natural Language module 216--a parser in this module, governed by the language understanding (semantics) rules or models to produce a parse tree (parse trees for ambiguous input) for the input string. The parse tree is then translated into an expression (or set of expressions) which represents the meaning of the input string and which is interpretable by CPU 224. A wide variety of grammar formalisms and parsing strategies have been developed, and will not be described in further detail herein.
VAC control module 218 performs administrative functions for VAC adjunct 114, such as providing a user interface, housekeeping tasks and command and control. VAC control module 218 also maintains and updates each user profile, which includes personally-configured lists of names or selected generic lists provided by a service ("VAC lists") as well as additional attributes found by VAC adjunct 114. Each user profile is stored in database 234.
It is noted that each module 210, 212, 214, 216, 218 are shown as separate functional modules in FIG. 2. The functionality of each of modules 210, 212, 214, 216, and 218 may be implemented in hardware, software, or a combination of hardware and software, using well known signal processing and statistical techniques. The functioning of each of these modules will be described in further detail below with reference to FIG. 3.
FIG. 3 is a block flow diagram of the steps performed by a VAC adjunct in accordance with one embodiment of the invention. As shown in FIG. 3, a call is connected to VAC adjunct 114 at step 300. A call is initiated from telephone 100. The call gets routed to LEC 102 which forwards the call to switch 104. Upon receipt of the call, switch 104 in turn routes the call to VAC adjunct 114 via communication network 106 and link 124. Thus, there is established an audio channel between telephone 100 and VAC adjunct 114.
Once an audio channel has been established, the user is presented with application-specific options, including initially configuring or modifying a personal user profile with lists of names or telephone numbers to be automatically dialed by VAC adjunct 114. Preselected lists may also be made available for selection by the user.
If the user wants to initially configure or modify a list, VAC control module 218 prompts the user to enter a first information item at step 302. This information item would be some sort of unique identifier for the person being added to the list. For example, the first information item could be a ten-digit telephone number, an electronic mail address, a social security number, a personal information number (PIN), URL and so forth. Although in this embodiment of the invention the first information item (also referred to as a "seed") is received by module 218 as a voice entry, it can be appreciated that the first information could also be a text entry, e.g., using the telephone keypad or computer keyboard.
Once module 218 receives the first information item, it then begins searching all available resources at step 304 for additional information items or attributes indexed by the first information item. Examples of additional attributes include, without limitation, a home address, a home telephone number, a work address, a work telephone number, a facsimile number, a mobile telephone number, a pager number, an email address, a home page URL, a neighboring address, local emergency service telephone numbers or addresses, and so forth. For example, module 218 could search database 234 for additional attributes. Module 218 could also establish a WWW link with web server 120 or database 118 and search one or both. Particular useful sources of additional attributes would include electronic white pages, electronic yellow pages, human resource database files, documents written in Hyper Text Markup Language (HTML) such as documents stored on one or more servers associated with the Internet or WWW, and so forth. Each additional attribute would be given a unique identifier and stored in database 234 as part of the personal user profile for that particular initial information item.
In addition to searching various resources based on the first information item, additional searches could be performed on the retrieved additional information items based on several factors, such as the number of available resources, the number of additional information items found, time limitations, and so forth. Thus, module 218 tests whether the search is complete at step 306. If additional information items are required or desired, then module 218 performs an additional search based on the information items retrieved from the prior search at step 305. If the search is complete at step 306, the additional information items are given to natural language interface module 216 to build a grammar using the retrieved information items. Module 216 builds the grammar at step 308 using techniques that are well known in the art, and therefore will not be described in detail herein. Finally, the user profile is updated and stored in database 234 at step 310.
The operation of VAC adjunct 114 will be described using the following example. Assume that a first user (i.e., the caller) dials the number "1-800-555-1212" to gain access to VAC adjunct 114. The call connection request is sent to LEC 102, which forwards it to switch 104. Switch 104 recognizes the number and routes the call to VAC adjunct 114 via communication network 106. Once connected to VAC adjunct 114, the first user requests to update his or her VAC list to include a second user (i.e., the person being called). VAC control module 218 prompts the first user for a unique identifier for the second user, and a unique word or phrase to automatically complete a call connection to the second user ("tag"). The first user enters the second user's telephone number, and the word "Daddy." Module 218 associates the word "Daddy" to the second user's telephone number. Thus, whenever the first user connects to VAC adjunct 114 and speaks the phrase "call daddy," VAC adjunct 114 attempts to complete a call connection to the telephone number associated with the word "Daddy," which in this example is the second user's telephone number. Thus, the first user's VAC list at a first point appears as follows:
______________________________________Voice Label Telephone Number______________________________________Dutton-Narayan-Zeljkovic 1-4-6 908-555-1212<call daddy>______________________________________
In accordance with the principles of this embodiment of the present invention, VAC adjunct 114 attempts to expand the words or phrases that can be spoken to initiate a call request to the second user's telephone number. VAC adjunct 114 opens a connection to web server 120 which stores electronic white page files. Module 218 submits a request to search the files using the second user's telephone number. Web server 120 sends back the second user's FULL NAME "Joe Smith" and HOME ADDRESS "885 South Avenue, Westfield, N.J. 07090" to module 218. Module 218 passes this information to natural language interface module 216 which uses the second user's FULL NAME and ADDRESS to expand the natural language grammar associated with the second user's telephone number. Thus, the first user's VAC list at a second point appears as follows:
______________________________________Voice Label Telephone Number______________________________________<call daddy> 908-555-1212<call joe><call smith><call joe smith in westfield><call daddy in westfield new jersey><call daddy in new jersey>______________________________________
The extent and level of details of the construction of the enhanced grammar for each VAC list may be changed in accordance with particular system design factors.
In another example, assume for the moment that the second user has a particular tag associated with more than one telephone number. VAC adjunct 114 can use search results, e.g., addresses, to resolve ambiguities between each telephone number. For example, assume the first user's VAC list appears as follows:
______________________________________Voice Label Telephone Number______________________________________Dutton-Narayan-Zeljkovic 1-4-6 908-555-1212, 908-555-1111<call daddy>______________________________________
By retrieving the corresponding addresses for each number, VAC adjunct 114 can construct the grammar shown at the second point above. Further, knowledge can be incorporated in the grammar regarding "home" or "work" or even "name of the work" place by searching the appropriate databases. For example, module 218 searches database 118 and retrieves the ADDRESS corresponding to the first number, and an ADDRESS2, "AT&T, 200 Laurel Avenue, Middletown, N.J. 07748," corresponding to the second number. Through a set of rules or heuristics, module 218 infers whether the address is a business address or a home address. This inference could be made based on the general characteristics of the area located by the address (e.g., business district versus residential), from which database the information was found (e.g., electronic white pages versus electronic yellow pages), and so forth. This information would be passed to natural language interface module 216 to build the following grammar:
______________________________________Voice Label Telephone Number______________________________________<call daddy> 908-555-1212<call joe><call smith><call joe smith in westfield><call daddy in westfield new jersey><call daddy in new jersey><call daddy at home><call daddy at work> 908-555-1111<call daddy at middletown><call joe at AT&T><call smith at work>. . . and so on.______________________________________
In yet another example, the principles of the present invention could be further expanded to provide additional inferences or extrapolations. For example, assume there are four telephone numbers associated with a single tag, such as follows:
______________________________________Voice Label Telephone Number______________________________________<grandma> phone1, phone2, phone3, phone4______________________________________
Module 218 searches various databases and finds that one of the telephone numbers is in New Jersey, one in Connecticut, one in Palm Beach, Fla., and one in Orlando, Fla. Module 216 could construct a grammar as follows:
call<grandma> in<NJ> phone 1
call<grandma> in<CT> phone 2
call<grandma> in<FL/Palm Beach> phone 3
call<grandma> in<FL/Orlando> phone 4.
In yet another embodiment of the invention, the principles of the present invention could be used in cases of urgent need or emergency in contacting friends or relatives. Assume that a son in a critical situation requires information such as the telephone number of a neighbor to his mother whom he has unsuccessfully been able to contact. In many cases, the son has no knowledge of the telephone number or, even the names of the neighbors, and obtaining such information in a timely fashion may not be straightforward. VAC adjunct 114 could be configured to perform a "proximity search" of a database having electronic white pages for those names, addresses and telephone numbers of neighbors within five houses of mom's house. Module 216 could then construct a grammar that understands such voice commands as "call neighbor of grandma in Florida" or "call police for grandma in Florida."
In another example, assume the second user's telephone is a work number. VAC adjunct 114 could search an employee database to find the second user's co-workers, such as his supervisor or administrative assistant. Module 216 could then construct a grammar that understands such voice commands as "call joe's boss" or "call Mr. Smith's administrative assistant."
Although various embodiments are specifically illustrated and described herein, it will be appreciated that modifications and variations of the present invention are covered by the above teachings and are within the purview of the appended claims without departing from the spirit and intended scope of the invention. For example, although the Internet and WWW were specifically described as possible resources for additional attributes or information items, it can be appreciated that any number of databases such as human resource databases, public tax record databases or public real estate databases could be searched and still fall within the scope of the invention. Further, although a natural language interface was illustrated, it can be appreciated that any type of expert system or translation system can be utilized to interpret user voice commands and fall within the scope of the invention.
|Cited Patent||Filing date||Publication date||Applicant||Title|
|US4979206 *||Sep 18, 1989||Dec 18, 1990||At&T Bell Laboratories||Directory assistance systems|
|US5297183 *||Apr 13, 1992||Mar 22, 1994||Vcs Industries, Inc.||Speech recognition system for electronic switches in a cellular telephone or personal communication network|
|US5479488 *||Feb 8, 1994||Dec 26, 1995||Bell Canada||Method and apparatus for automation of directory assistance using speech recognition|
|US5574908 *||Jun 6, 1995||Nov 12, 1996||Asymetrix Corporation||Method and apparatus for generating a query to an information system specified using natural language-like constructs|
|US5617567 *||May 11, 1995||Apr 1, 1997||Financial System Technology Pty. Ltd.||Data processing system and method for retrieving and entity specified in a search path record from a relational database|
|1||"Directory Services--Beyond Easy Lookups" Computer Telephony Aug. 1996.|
|2||"Hypertext Transfer Protocol (HTTP) Working Draft of the Internet Engineering Task Force, 1993", by T. Berners-Lee, and D. Connolly, -HTTP: A protocol for networked information.|
|3||"Internetworking with TCP/IP: Principles, Protocols and Architecture", by Douglas Comer, Englewood Cliffs, NJ, Prentice Hall, 1988.|
|4||"Speech Rec Rules" CallCenter (Computer Telephony) Jun. 1996.|
|5||*||Directory Services Beyond Easy Lookups Computer Telephony Aug. 1996.|
|6||*||Hypertext Transfer Protocol (HTTP) Working Draft of the Internet Engineering Task Force, 1993 , by T. Berners Lee, and D. Connolly, HTTP: A protocol for networked information .|
|7||*||Internetworking with TCP/IP: Principles, Protocols and Architecture , by Douglas Comer, Englewood Cliffs, NJ, Prentice Hall, 1988.|
|8||*||Speech Rec Rules CallCenter (Computer Telephony) Jun. 1996.|
|Citing Patent||Filing date||Publication date||Applicant||Title|
|US6404859 *||May 6, 1999||Jun 11, 2002||Lockheed Martin Corporation||Voice enabled system for remote access of information|
|US6434529 *||Feb 16, 2000||Aug 13, 2002||Sun Microsystems, Inc.||System and method for referencing object instances and invoking methods on those object instances from within a speech recognition grammar|
|US6477240 *||Mar 31, 1999||Nov 5, 2002||Microsoft Corporation||Computer-implemented voice-based command structure for establishing outbound communication through a unified messaging system|
|US6499013 *||Sep 9, 1998||Dec 24, 2002||One Voice Technologies, Inc.||Interactive user interface using speech recognition and natural language processing|
|US6526382 *||Dec 7, 1999||Feb 25, 2003||Comverse, Inc.||Language-oriented user interfaces for voice activated services|
|US6574599||Mar 31, 1999||Jun 3, 2003||Microsoft Corporation||Voice-recognition-based methods for establishing outbound communication through a unified messaging system including intelligent calendar interface|
|US6591236 *||Apr 13, 1999||Jul 8, 2003||International Business Machines Corporation||Method and system for determining available and alternative speech commands|
|US6598022||Aug 13, 2002||Jul 22, 2003||Comverse Inc.||Determining promoting syntax and parameters for language-oriented user interfaces for voice activated services|
|US6604076 *||Nov 9, 2000||Aug 5, 2003||Koninklijke Philips Electronics N.V.||Speech recognition method for activating a hyperlink of an internet page|
|US6615172 *||Nov 12, 1999||Sep 2, 2003||Phoenix Solutions, Inc.||Intelligent query engine for processing voice based queries|
|US6665547 *||Dec 20, 1999||Dec 16, 2003||Nec Corporation||Radio communication apparatus with telephone number registering function through speech recognition|
|US6950793||Jan 10, 2002||Sep 27, 2005||International Business Machines Corporation||System and method for deriving natural language representation of formal belief structures|
|US6952676 *||Jul 11, 2001||Oct 4, 2005||Sherman William F||Voice recognition peripheral device|
|US6996531 *||Mar 30, 2001||Feb 7, 2006||Comverse Ltd.||Automated database assistance using a telephone for a speech based or text based multimedia communication mode|
|US7085723||Aug 16, 2001||Aug 1, 2006||International Business Machines Corporation||System and method for determining utterance context in a multi-context speech application|
|US7127402||Jan 10, 2002||Oct 24, 2006||International Business Machines Corporation||Method and apparatus for converting utterance representations into actions in a conversational system|
|US7139706||Aug 12, 2002||Nov 21, 2006||Comverse, Inc.||System and method of developing automatic speech recognition vocabulary for voice activated services|
|US7203188||May 21, 2002||Apr 10, 2007||Estara, Inc.||Voice-controlled data/information display for internet telephony and integrated voice and data communications using telephones and computing devices|
|US7212964 *||Mar 22, 2002||May 1, 2007||At&T Corp.||Language-understanding systems employing machine translation components|
|US7249018||Oct 25, 2001||Jul 24, 2007||International Business Machines Corporation||System and method for relating syntax and semantics for a conversational speech application|
|US7257537||Jan 10, 2002||Aug 14, 2007||International Business Machines Corporation||Method and apparatus for performing dialog management in a computer conversational interface|
|US7356130||Dec 30, 2004||Apr 8, 2008||International Business Machines Corporation||Method and system for selecting speech or DTMF interfaces or a mixture of both|
|US7363269 *||Jan 3, 2001||Apr 22, 2008||Ebs Group Limited||Conversational dealing system|
|US7376556||Mar 2, 2004||May 20, 2008||Phoenix Solutions, Inc.||Method for processing speech signal features for streaming transport|
|US7401023 *||Sep 6, 2000||Jul 15, 2008||Verizon Corporate Services Group Inc.||Systems and methods for providing automated directory assistance using transcripts|
|US7403938||Sep 20, 2002||Jul 22, 2008||Iac Search & Media, Inc.||Natural language query processing|
|US7426469 *||May 16, 2007||Sep 16, 2008||Eastern Investments Llc||Speech enabled computing method|
|US7430511 *||May 16, 2007||Sep 30, 2008||Eastern Investments, Llc||Speech enabled computing system|
|US7433823 *||May 16, 2007||Oct 7, 2008||Eastern Investments, Llc||Speech input disambiguation computing system|
|US7447636 *||May 12, 2005||Nov 4, 2008||Verizon Corporate Services Group Inc.||System and methods for using transcripts to train an automated directory assistance service|
|US7447637 *||Mar 2, 2007||Nov 4, 2008||Eastern Investments, Llc||System and method of processing speech within a graphic user interface|
|US7447638 *||May 16, 2007||Nov 4, 2008||Eastern Investments, Llc||Speech input disambiguation computing method|
|US7467081||Jan 22, 2007||Dec 16, 2008||At&T Corp.||Language-understanding training database action pair augmentation using bidirectional translation|
|US7496508 *||Apr 18, 2002||Feb 24, 2009||Koninklijke Philips Electronics N.V.||Method of determining database entries|
|US7496514||Jul 16, 2007||Feb 24, 2009||International Business Machines Corporation||Method and Apparatus for managing dialog management in a computer conversation|
|US7647225||Nov 20, 2006||Jan 12, 2010||Phoenix Solutions, Inc.||Adjustable resource based speech recognition system|
|US7657424||Dec 3, 2004||Feb 2, 2010||Phoenix Solutions, Inc.||System and method for processing sentence based queries|
|US7672841||May 19, 2008||Mar 2, 2010||Phoenix Solutions, Inc.||Method for processing speech data for a distributed recognition system|
|US7698131||Apr 9, 2007||Apr 13, 2010||Phoenix Solutions, Inc.||Speech recognition system for client devices having differing computing capabilities|
|US7702508||Dec 3, 2004||Apr 20, 2010||Phoenix Solutions, Inc.||System and method for natural language processing of query answers|
|US7725307||Aug 29, 2003||May 25, 2010||Phoenix Solutions, Inc.||Query engine for processing voice based queries including semantic decoding|
|US7725320||Apr 9, 2007||May 25, 2010||Phoenix Solutions, Inc.||Internet based speech recognition system with dynamic grammars|
|US7725321||Jun 23, 2008||May 25, 2010||Phoenix Solutions, Inc.||Speech based query system using semantic decoding|
|US7729904||Dec 3, 2004||Jun 1, 2010||Phoenix Solutions, Inc.||Partial speech processing device and method for use in distributed systems|
|US7827035 *||Sep 29, 2008||Nov 2, 2010||Nuance Communications, Inc.||Speech recognition system and method|
|US7831426||Jun 23, 2006||Nov 9, 2010||Phoenix Solutions, Inc.||Network based interactive speech recognition system|
|US7873519||Oct 31, 2007||Jan 18, 2011||Phoenix Solutions, Inc.||Natural language speech lattice containing semantic variants|
|US7912702||Oct 31, 2007||Mar 22, 2011||Phoenix Solutions, Inc.||Statistical language model trained with semantic variants|
|US7912726||Aug 30, 2005||Mar 22, 2011||At&T Intellectual Property Ii, L.P.||Method and apparatus for creation and user-customization of speech-enabled services|
|US7917497||Apr 18, 2008||Mar 29, 2011||Iac Search & Media, Inc.||Natural language query processing|
|US7940746||Aug 24, 2004||May 10, 2011||Comcast Cable Holdings, Llc||Method and system for locating a voice over internet protocol (VoIP) device connected to a network|
|US8000974 *||Oct 18, 2010||Aug 16, 2011||Nuance Communications, Inc.||Speech recognition system and method|
|US8073683||Dec 16, 2008||Dec 6, 2011||At&T Intellectual Property Ii, L.P.||Language-understanding training database action pair augmentation using bidirectional translation|
|US8175883 *||Jul 8, 2011||May 8, 2012||Nuance Communications, Inc.||Speech recognition system and method|
|US8229734||Jun 23, 2008||Jul 24, 2012||Phoenix Solutions, Inc.||Semantic decoding of user queries|
|US8312042 *||Sep 26, 2011||Nov 13, 2012||Google Inc.||Automatic routing of search results|
|US8340970||Apr 11, 2012||Dec 25, 2012||Nuance Communications, Inc.||Methods and apparatus for initiating actions using a voice-controlled interface|
|US8346555||Aug 22, 2006||Jan 1, 2013||Nuance Communications, Inc.||Automatic grammar tuning using statistical language model generation|
|US8352277||Apr 9, 2007||Jan 8, 2013||Phoenix Solutions, Inc.||Method of interacting through speech with a web-connected server|
|US8386608 *||Aug 3, 2007||Feb 26, 2013||Alex Rankov||Service scripting framework|
|US8392411||Aug 6, 2010||Mar 5, 2013||Google Inc.||Automatic routing of search results|
|US8396710 *||Nov 23, 2011||Mar 12, 2013||Ben Franklin Patent Holding Llc||Distributed voice user interface|
|US8438031||Jun 7, 2007||May 7, 2013||Nuance Communications, Inc.||System and method for relating syntax and semantics for a conversational speech application|
|US8630858||Sep 14, 2012||Jan 14, 2014||Nuance Communications, Inc.||Methods and apparatus for initiating actions using a voice-controlled interface|
|US8689203||Feb 19, 2008||Apr 1, 2014||Microsoft Corporation||Software update techniques based on ascertained identities|
|US8719281||Mar 4, 2013||May 6, 2014||Google Inc.||Automatic dialing|
|US8724522||Jan 25, 2011||May 13, 2014||Comcast Cable Holdings, Llc||Method and system for locating a voice over internet protocol (VoIP) device connected to a network|
|US8762152||Oct 1, 2007||Jun 24, 2014||Nuance Communications, Inc.||Speech recognition system interactive agent|
|US8762155||Sep 22, 2011||Jun 24, 2014||Intellectual Ventures I Llc||Voice integration platform|
|US8923499||Feb 8, 2005||Dec 30, 2014||Wavport, L.L.C.||Apparatus and method for providing enhanced telecommunications services|
|US8954325 *||Mar 22, 2004||Feb 10, 2015||Rockstar Consortium Us Lp||Speech recognition in automated information services systems|
|US9036626||Mar 25, 2014||May 19, 2015||Comcast Cable Holdings, Llc||Method and system for locating a voice over internet protocol (VOIP) device connected to a network|
|US9049132||Mar 3, 2015||Jun 2, 2015||Comcast Cable Holdings, Llc||Locating a voice over packet (VoP) device connected to a network|
|US9055550||Mar 6, 2015||Jun 9, 2015||Comcast Cable Holdings, Llc||Locating a voice over packet (VoP) device connected to a network|
|US9076448||Oct 10, 2003||Jul 7, 2015||Nuance Communications, Inc.||Distributed real time speech recognition system|
|US9190063||Oct 31, 2007||Nov 17, 2015||Nuance Communications, Inc.||Multi-language speech recognition system|
|US9286294||Aug 3, 2001||Mar 15, 2016||Comcast Ip Holdings I, Llc||Video and digital multimedia aggregator content suggestion engine|
|US9412379||Sep 16, 2014||Aug 9, 2016||Toyota Motor Engineering & Manufacturing North America, Inc.||Method for initiating a wireless communication link using voice recognition|
|US9648644||Jun 5, 2015||May 9, 2017||Comcast Cable Communications, Llc||Determining a location of a device for calling via an access point|
|US9813641||Jun 3, 2015||Nov 7, 2017||Comcast Ip Holdings I, Llc||Method and apparatus for targeting of interactive virtual objects|
|US20020065662 *||Jul 11, 2001||May 30, 2002||Sherman William F.||Voice recognition peripheral device|
|US20020072914 *||Dec 8, 2000||Jun 13, 2002||Hiyan Alshawi||Method and apparatus for creation and user-customization of speech-enabled services|
|US20020095286 *||Oct 25, 2001||Jul 18, 2002||International Business Machines Corporation||System and method for relating syntax and semantics for a conversational speech application|
|US20020133354 *||Aug 16, 2001||Sep 19, 2002||International Business Machines Corporation||System and method for determining utterance context in a multi-context speech application|
|US20020133355 *||Jan 10, 2002||Sep 19, 2002||International Business Machines Corporation||Method and apparatus for performing dialog management in a computer conversational interface|
|US20020138266 *||Jan 10, 2002||Sep 26, 2002||International Business Machines Corporation||Method and apparatus for converting utterance representations into actions in a conversational system|
|US20020143548 *||Mar 30, 2001||Oct 3, 2002||Toby Korall||Automated database assistance via telephone|
|US20020143685 *||Jan 3, 2001||Oct 3, 2002||Ebs Service Company Limited||Conversational dealing system|
|US20020152300 *||Apr 11, 2002||Oct 17, 2002||Koninklijke Philips Electronics N.V.||Internet shopping assistant|
|US20020169751 *||Apr 18, 2002||Nov 14, 2002||Stefanie Krass||Method of determining database entries|
|US20020173960 *||Jan 10, 2002||Nov 21, 2002||International Business Machines Corporation||System and method for deriving natural language representation of formal belief structures|
|US20030004719 *||Aug 12, 2002||Jan 2, 2003||Comverse Network Systems, Inc.||Language-oriented user interfaces for voice activated services|
|US20030069880 *||Sep 20, 2002||Apr 10, 2003||Ask Jeeves, Inc.||Natural language query processing|
|US20030144846 *||Jan 31, 2002||Jul 31, 2003||Denenberg Lawrence A.||Method and system for modifying the behavior of an application based upon the application's grammar|
|US20040019488 *||Jul 23, 2002||Jan 29, 2004||Netbytel, Inc.||Email address recognition using personal information|
|US20040249635 *||Mar 2, 2004||Dec 9, 2004||Bennett Ian M.||Method for processing speech signal features for streaming transport|
|US20050152521 *||Feb 8, 2005||Jul 14, 2005||Liljestrand Keith A.||Apparatus and method for providing enhanced telecommunications services|
|US20050169440 *||Dec 30, 2004||Aug 4, 2005||International Business Machines Corporation||Method and system for selecting speech or DTMF interfaces or a mixture of both|
|US20060004575 *||Aug 30, 2005||Jan 5, 2006||At&T Corp.||Method and apparatus for creation and user-customization of speech-enabled services|
|US20070118352 *||Jan 22, 2007||May 24, 2007||At&T Corp.||Language-understanding systems employing machine translation components|
|US20070265847 *||Jun 7, 2007||Nov 15, 2007||Ross Steven I||System and Method for Relating Syntax and Semantics for a Conversational Speech Application|
|US20080015864 *||Jul 16, 2007||Jan 17, 2008||Ross Steven I||Method and Apparatus for Managing Dialog Management in a Computer Conversation|
|US20080052076 *||Aug 22, 2006||Feb 28, 2008||International Business Machines Corporation||Automatic grammar tuning using statistical language model generation|
|US20080263019 *||Apr 18, 2008||Oct 23, 2008||Iac Search & Media, Inc.||Natural language query processing|
|US20090024391 *||Sep 29, 2008||Jan 22, 2009||Eastern Investments, Llc||Speech recognition system and method|
|US20090097627 *||Feb 8, 2005||Apr 16, 2009||Liljestrand Keith A||Apparatus and method for providing enhanced telecommunications services|
|US20090210868 *||Feb 19, 2008||Aug 20, 2009||Microsoft Corporation||Software Update Techniques|
|US20090248397 *||Mar 25, 2008||Oct 1, 2009||Microsoft Corporation||Service Initiation Techniques|
|US20110029316 *||Oct 18, 2010||Feb 3, 2011||Nuance Communications, Inc.||Speech recognition system and method|
|US20120015674 *||Sep 26, 2011||Jan 19, 2012||Google Inc.||Automatic Routing of Search Results|
|US20120072221 *||Nov 23, 2011||Mar 22, 2012||Ben Franklin Patent Holding, Llc||Distributed voice user interface|
|WO2002086865A1 *||Apr 9, 2002||Oct 31, 2002||Koninklijke Philips Electronics N.V.||Speaker verification in a spoken dialogue system|
|U.S. Classification||704/275, 704/E15.026, 715/210, 704/270, 704/E15.04, 704/257, 715/234, 704/9, 704/10, 707/999.002, 707/999.004, 707/999.005, 707/999.003|
|International Classification||G10L15/06, G10L15/18, G10L15/22|
|Cooperative Classification||Y10S707/99932, Y10S707/99933, Y10S707/99934, Y10S707/99935, G10L2015/0631, G10L15/22, G10L15/1822|
|European Classification||G10L15/22, G10L15/18U|
|Apr 14, 1998||AS||Assignment|
Owner name: AT&T CORP., NEW YORK
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:DUTTON, DAWN L.;NARAYANAN, SHRIKANTH SAMBASIVAN;ZELIJKOVIC, ILIJA;REEL/FRAME:009156/0379
Effective date: 19980409
|Mar 29, 2004||FPAY||Fee payment|
Year of fee payment: 4
|Mar 20, 2008||FPAY||Fee payment|
Year of fee payment: 8
|Mar 23, 2012||FPAY||Fee payment|
Year of fee payment: 12
|Mar 28, 2016||AS||Assignment|
Owner name: AT&T PROPERTIES, LLC, NEVADA
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:AT&T CORP.;REEL/FRAME:038274/0841
Effective date: 20160204
Owner name: AT&T INTELLECTUAL PROPERTY II, L.P., GEORGIA
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:AT&T PROPERTIES, LLC;REEL/FRAME:038274/0917
Effective date: 20160204
|Jan 26, 2017||AS||Assignment|
Owner name: NUANCE COMMUNICATIONS, INC., MASSACHUSETTS
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:AT&T INTELLECTUAL PROPERTY II, L.P.;REEL/FRAME:041498/0316
Effective date: 20161214